Wenlai ZHAO

Wenlai ZHAO is an Assistant Professor in the Department of Computer Science and Technology at Tsinghua University. His research interests include Parallel Computing, Custom Computing, and AI Computing Systems. His work focuses on the design and optimization of reconfigurable acceleration units, AI algorithm libraries, and parallel frameworks for domestic many-core high-performance processors. He has contributed to the optimization and deployment of large-scale AI applications on supercomputers. His publications include research on large-scale automatic K-means clustering, cognitive caching, and parallel design for Cryo-EM structure determination. He has also worked on scaling the training of recurrent neural networks and optimizing convolutional neural networks on supercomputers.

Wenlai Zhao is a researcher at Tsinghua University specializing in Deep Learning and High Performance Computing. Their work focuses on optimizing deep learning frameworks for high-performance computing environments, particularly on supercomputers like the Sunway Taihulight. Zhao has developed FPGA-based frameworks for training convolutional neural networks and parallel libraries for accelerating deep learning applications. They have also explored transformer models for time series forecasting and hybrid architectures for energy-efficient computing. Research includes optimizing CNNs, improving wireless caching, and parallelizing cryo-EM reconstruction on GPU clusters. Zhao's contributions emphasize scalable, efficient, and energy-aware computing solutions for complex data-driven applications.